© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75780
    Prev
    Next
    INDEX
    Explanations

    junior or senior developer roles

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly fires on tokens containing numbers or digits, i.e. numerical data in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hões
    -0.91
    ociação
    -0.81
     lecker
    -0.73
    فاف
    -0.71
    znam
    -0.71
    wają
    -0.70
    enteuer
    -0.70
     הול
    -0.70
    +")
    -0.69
     упаковке
    -0.69
    POSITIVE LOGITS
     developer
    2.34
     developers
    2.25
     Developers
    1.86
     Developer
    1.86
     programmer
    1.81
     programmers
    1.76
    Developer
    1.74
    Developers
    1.73
     coding
    1.73
     devs
    1.67
    Activations Density 0.173%

    No Known Activations